Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/openload.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_chr
   8 from ..utils import (
   9     determine_ext,
  10     ExtractorError,
  11 )
  12
  13
  14 class OpenloadIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:openload\.(?:co|io)|oload\.tv)/(?:f|embed)/(?P<id>[a-zA-Z0-9-_]+)'
  16
  17     _TESTS = [{
  18         'url': 'https://openload.co/f/kUEfGclsU9o',
  19         'md5': 'bf1c059b004ebc7a256f89408e65c36e',
  20         'info_dict': {
  21             'id': 'kUEfGclsU9o',
  22             'ext': 'mp4',
  23             'title': 'skyrim_no-audio_1080.mp4',
  24             'thumbnail': r're:^https?://.*\.jpg$',
  25         },
  26     }, {
  27         'url': 'https://openload.co/embed/rjC09fkPLYs',
  28         'info_dict': {
  29             'id': 'rjC09fkPLYs',
  30             'ext': 'mp4',
  31             'title': 'movie.mp4',
  32             'thumbnail': r're:^https?://.*\.jpg$',
  33             'subtitles': {
  34                 'en': [{
  35                     'ext': 'vtt',
  36                 }],
  37             },
  38         },
  39         'params': {
  40             'skip_download': True,  # test subtitles only
  41         },
  42     }, {
  43         'url': 'https://openload.co/embed/kUEfGclsU9o/skyrim_no-audio_1080.mp4',
  44         'only_matching': True,
  45     }, {
  46         'url': 'https://openload.io/f/ZAn6oz-VZGE/',
  47         'only_matching': True,
  48     }, {
  49         'url': 'https://openload.co/f/_-ztPaZtMhM/',
  50         'only_matching': True,
  51     }, {
  52         # unavailable via https://openload.co/f/Sxz5sADo82g/, different layout
  53         # for title and ext
  54         'url': 'https://openload.co/embed/Sxz5sADo82g/',
  55         'only_matching': True,
  56     }, {
  57         'url': 'https://oload.tv/embed/KnG-kKZdcfY/',
  58         'only_matching': True,
  59     }]
  60
  61     @staticmethod
  62     def _extract_urls(webpage):
  63         return re.findall(
  64             r'<iframe[^>]+src=["\']((?:https?://)?(?:openload\.(?:co|io)|oload\.tv)/embed/[a-zA-Z0-9-_]+)',
  65             webpage)
  66
  67     def _real_extract(self, url):
  68         video_id = self._match_id(url)
  69         webpage = self._download_webpage('https://openload.co/embed/%s/' % video_id, video_id)
  70
  71         if 'File not found' in webpage or 'deleted by the owner' in webpage:
  72             raise ExtractorError('File not found', expected=True)
  73
  74         ol_id = self._search_regex(
  75             '<span[^>]+id="[^"]+"[^>]*>([0-9A-Za-z]+)</span>',
  76             webpage, 'openload ID')
  77
  78         first_char = int(ol_id[0])
  79         urlcode = []
  80         num = 1
  81
  82         while num < len(ol_id):
  83             i = ord(ol_id[num])
  84             key = 0
  85             if i <= 90:
  86                 key = i - 65
  87             elif i >= 97:
  88                 key = 25 + i - 97
  89             urlcode.append((key, compat_chr(int(ol_id[num + 2:num + 5]) // int(ol_id[num + 1]) - first_char)))
  90             num += 5
  91
  92         video_url = 'https://openload.co/stream/' + ''.join(
  93             [value for _, value in sorted(urlcode, key=lambda x: x[0])])
  94
  95         title = self._og_search_title(webpage, default=None) or self._search_regex(
  96             r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
  97             'title', default=None) or self._html_search_meta(
  98             'description', webpage, 'title', fatal=True)
  99
 100         entries = self._parse_html5_media_entries(url, webpage, video_id)
 101         subtitles = entries[0]['subtitles'] if entries else None
 102
 103         info_dict = {
 104             'id': video_id,
 105             'title': title,
 106             'thumbnail': self._og_search_thumbnail(webpage, default=None),
 107             'url': video_url,
 108             # Seems all videos have extensions in their titles
 109             'ext': determine_ext(title, 'mp4'),
 110             'subtitles': subtitles,
 111         }
 112         return info_dict